{"slug": "why-intent-prediction-needs-more-than-an-llm", "title": "Why intent prediction needs more than an…", "summary": "Yobi CTO Frank Portman explains why next-token prediction is insufficient for forecasting human behavior, detailing how the company builds a 'foundation model of behavior' using transformers and graph neural networks instead of chat-style LLMs to run millions of personalization decisions per second while preserving consumer data privacy.", "body_md": "Ryan sits down with Frank Portman, CTO at Yobi, to talk about why next-token prediction, though great for language, isn’t the right inductive bias for forecasting human behavior. They discuss how Yobi builds a “foundation model of behavior” using transformers and graph neural networks instead of chat-style LLMs, and what it takes to run millions of personalization decisions per second while keeping consumer data private.", "url": "https://wpnews.pro/news/why-intent-prediction-needs-more-than-an-llm", "canonical_source": "https://stackoverflow.blog/2026/06/30/why-intent-prediction-needs-more-than-an-llm/", "published_at": "2026-06-30 04:50:11.800054+00:00", "updated_at": "2026-06-30 04:50:13.633296+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "ai-products", "ai-infrastructure", "ai-ethics"], "entities": ["Yobi", "Frank Portman", "transformers", "graph neural networks"], "alternates": {"html": "https://wpnews.pro/news/why-intent-prediction-needs-more-than-an-llm", "markdown": "https://wpnews.pro/news/why-intent-prediction-needs-more-than-an-llm.md", "text": "https://wpnews.pro/news/why-intent-prediction-needs-more-than-an-llm.txt", "jsonld": "https://wpnews.pro/news/why-intent-prediction-needs-more-than-an-llm.jsonld"}}